Radar de seguridad e inteligencia artificial
Noticias
Revisamos cada hora los feeds públicos de 60 fuentes de referencia y clasificamos cada titular por tema y severidad. Aquí verás el titular y un extracto breve: la noticia se lee en su fuente original.
en 24 horas
semana
crítica
en seguimiento
Actualización horaria Última revisión hace 56 min 964 titulares en el archivo
Qué se está publicando
Distribución por tema
325 titulares en Seguridad IA Limpiar filtros ×
- domingo 19 jul
-
Autonomous AI Intrusions Are Here: Lessons from the Hugging Face Compromise
Hugging Face disclosed an intrusion that, according to them, was driven end to end by an autonomous AI agent system. Along similar lines, Sysdig recently published a blog on JADEPUFFER, which it assesses to be an agent-driven ransomware…
Embrace The Red Seguridad IA embracethered.com - jueves 16 jul
-
From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal
This is a follow-up to my previous Terminal DiLLMa research, and there is a positive outcome: Apple fixed a macOS Terminal behavior that enabled a DNS-based data exfiltration technique. DNS Requests via ANSI Escape Codes David Leadbeater…
Embrace The Red Seguridad IA embracethered.com - jueves 9 jul
-
Up the Stack: How AI’s Escape From the Commodity Trap Risks Enterprise Lock-in
Critics and boosters are both looking in the wrong place
AI Snake Oil Seguridad IA normaltech.ai - miércoles 8 jul
-
HPC AI Workloads Need Runtime Security. The Architecture Already Exists.
Learn how to secure HPC AI infrastructure against runtime and supply chain threats via continuous behavioral monitoring.
SentinelOne Seguridad IA sentinelone.com - miércoles 1 jul
-
Silver Bullet Security Podcast 158 – Artem Dinaburg
View on Zencastr On Episode 158 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Artem Dinaburg. Artem talks about using Agentic AI to find, fix, and exploit software security defects. We talk decompilation, stochasticism…
Berryville Institute (BIML) Seguridad IA berryvilleiml.com -
The Autonomous SOC, Revisited: What 18 Months on the Road Has Taught Us
Explore SentinelOne's Autonomous SOC maturity model to map your journey toward AI autonomy through strict governance.
SentinelOne Seguridad IA sentinelone.com - jueves 25 jun
-
Computer-Use and TOCTOU: What You Click Is Not What You Get!
Last year, Jun Kokatsu disclosed an interesting vulnerability with ChatGPT Operator by exploiting a race condition. I was wondering if I could reproduce this attack chain, and this post describes the results of that research. I had this…
Embrace The Red Seguridad IA embracethered.com - jueves 18 jun
-
Aikido and OWASP bring agentic Code Audit to the global AppSec community
Aikido Security and OWASP launch a new individual member benefit: pentester-grade code audits, powered by AI reasoning. Gent, Belgium [June 18th, 2026] Aikido Security, the all-in-one developer security platform, today announced a new…
OWASP Seguridad IA owasp.org - miércoles 17 jun
-
BIML in the Barn — Important Talks on AI and Machine Learning Security are Happening Here
BIML in the Barn series is an important part of our mission at BIML. We are sparking compelling and insightful talks on AI and machine learning security by bringing leading researchers and experts to our global HQ in Berryville, Virginia…
Berryville Institute (BIML) Seguridad IA berryvilleiml.com -
The Agentic SOC: Solving Security’s Investigation Capacity Crisis in the Frontier AI Era
SentinelOne’s Purple AI Agentic Investigation, now GA, solves the SOC investigation capacity gap with zero-click, machine-speed alert analysis.
SentinelOne Seguridad IA sentinelone.com - domingo 14 jun
-
Anthropic versus US Administration: Fable, Mythos, and the Cyber Cyber
Who wins when the FUD is turned to 11 and the irony is thick enough to cut with a knife? BIML spoke to German TV about that. Have a watch. To prep for the interview by gathering our thoughts, we wrote this.
Berryville Institute (BIML) Seguridad IA berryvilleiml.com - sábado 13 jun
-
Irony: The US Government Issues an Export Control Directive for Fable 5 and Mythos 5
Anthropic, June 12, 2026 “The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States…
Berryville Institute (BIML) Seguridad IA berryvilleiml.com - viernes 12 jun
-
GUEST BLOG: Your Frontier Provider Is Quietly Limiting Your Capability & Research
We think this blog entry by starseer.ai CEO Tim Schulz is important enough that we asked for permission to reprint it here. Do us a favor and check out starseer’s white box offerings—opening the black box of AI so you know what’s going on…
Berryville Institute (BIML) Seguridad IA berryvilleiml.com - miércoles 10 jun
-
Why AI hasn’t replaced software engineers, and won’t
Coding agents as normal technology
AI Snake Oil Seguridad IA normaltech.ai - viernes 22 may
-
Did Google’s AI agents really build an operating system for $916?
The importance of independent evaluation
AI Snake Oil Seguridad IA normaltech.ai - jueves 21 may
-
Do AI Risks Require Extraordinary Government Intervention?
Let’s not skip the hard work of AI governance
AI Snake Oil Seguridad IA normaltech.ai - jueves 14 may
-
Pwn2Own Berlin 2026 - Day One Results
Welcome to Day One of Pwn2Own Berlin 2026! Today, 22 entries took the Pwn2Own stage to target AI Databases, Coding Agents, Local Inferences, and a separate category for NVIDIA products, as the world’s top security researchers push…
Zero Day Initiative Seguridad IA thezdi.com - miércoles 13 may
-
Juice Shop v20.0.0 — a fresh squeeze of features, now with AI
Juice Shop v20.0.0 — a fresh squeeze of features, now with AI After months of work on the develop branch, OWASP Juice Shop v20.0.0 is ready to serve. This is a major version bump packed with new challenges, a redesigned storefront, and a…
OWASP Seguridad IA owasp.org - lunes 4 may
-
Copirate 365 at DEF CON: Plundering in the Depths of Microsoft Copilot (CVE-2026-24299)
This is a writeup of my DEF CON Singapore talk that walks through vulnerabilities and exploits in M365 Copilot and Consumer Copilot. I disclosed these to Microsoft last year. MSRC assigned CVE-2026-24299 and the issues are now patched…
Embrace The Red Seguridad IA embracethered.com - jueves 23 abr
-
AI threats in the wild: The current state of prompt injections on the web
Posted by Thomas Brunner, Yu-Han Liu, Moni PandeAt Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now…
Google Security Blog Seguridad IA security.googleblog.com - viernes 17 abr
-
Breaking Opus 4.7 with ChatGPT (Hacking Claude's Memory)
In this post, we explore how ChatGPT generated an adversarial image that hijacked my Claude Opus 4.7 to invoke the memory tool and persist false memories for future chats. This matters because Opus 4.6+ is genuinely a lot harder to attack…
Embrace The Red Seguridad IA embracethered.com - jueves 2 abr
-
Mitigating prompt injection attacks with a layered defense strategy
Posted by Adam Gavish, Google GenAI Security TeamWith the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is…
Google Security Blog Seguridad IA security.googleblog.com -
Google Workspace’s continuous approach to mitigating indirect prompt injections
Posted by Adam Gavish, Google GenAI Security TeamIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the…
Google Security Blog Seguridad IA security.googleblog.com - miércoles 18 mar
-
Staying One Step Ahead: Strengthening Android’s Lead in Scam Protection
Posted by Lyubov Farafonova, Product Manager, Phone by Google; Alberto Pastor Nieto, Sr. Product Manager Google Messages and RCS Spam and Abuse We’ve shared how Android’s proactive, multi-layered scam defenses utilize Google AI to protect…
Google Security Blog Seguridad IA security.googleblog.com - miércoles 11 mar
-
Windows and macOS Malware Spreads via Fake “Claude Code” Google Ads
Bitdefender’s security researchers have discovered a malicious Google Ads campaign targeting anyone searching for downloads related to Claude, the large language model developed by Anthropic.
Bitdefender Labs Seguridad IA bitdefender.com
Del titular al control
Leer noticias no reduce el riesgo
En el blog publicamos análisis propios que traducen esto en decisiones: qué controlar primero, con qué evidencia y en qué orden.